基于重构暗通道的二次正弦衰减的去雾算法

doi:10.12305/j.issn.1001-506X.2021.05.02

系统工程与电子技术 ›› 2021, Vol. 43 ›› Issue (5): 1169-1175.doi: 10.12305/j.issn.1001-506X.2021.05.02

基于重构暗通道的二次正弦衰减的去雾算法

梅葳*(), 李昕()

上海大学机电工程与自动化学院, 上海 200072

收稿日期:2020-05-22 出版日期:2021-05-01 发布日期:2021-04-27
通讯作者: 梅葳 E-mail:meiweihello@163.com;su_xinli@aliyun.com
作者简介:梅葳(1995—), 男, 硕士研究生, 主要研究方向为单幅图像去雾算法研究。E-mail: meiweihello@163.com|李昕(1970—), 男, 副研究员, 硕士研究生导师, 博士，主要研究方向为语音识别、智能机器人及应用。E-mail: su_xinli@aliyun.com
基金资助:
国家自然科学基金(61877065);上海市科学技术委员会科研计划(14DZ1206302)

Dehazing algorithm based on reconstructed dark channel with quadratic sinusoidal attenuation

Wei MEI*(), Xin LI()

School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200072, China

Received:2020-05-22 Online:2021-05-01 Published:2021-04-27
Contact: Wei MEI E-mail:meiweihello@163.com;su_xinli@aliyun.com

摘要/Abstract

摘要：

针对暗通道算法在天空区域失效以及最小值滤波器产生伪影现象等缺陷, 提出一种基于重构暗通道的二次正弦衰减的去雾算法。首先, 利用图像分割对原始图像进行暗通道重构得到重构暗通道。然后，设计雾密度权重函数对场景中的雾浓度做近似估计得到权重系数, 并结合权重系数对重构暗通道进行二次正弦衰减得到初始透射率。为了得到更加精细的透射率, 结合直方图均衡化和快速导向滤波来优化透射率。最后, 结合大气散射模型复原无雾图像。实验结果表明, 所提算法能有效处理天空区域, 抑制光晕伪影, 且复原图像细节明显, 亮度饱和度适宜。

关键词: 图像去雾, 正弦衰减, 透射率

Abstract:

Aiming at the defects such as the failure of the dark channel algorithm in the sky area and the halo phenomenon caused by the minimum filter, a dehazing algorithm based on the quadratic sinusoidal attenuation of the reconstructed dark channel is proposed. Firstly, the reconstruction dark channel is obtained by using image segmentation to reconstruct the original image. Then the hazy density weight function is designed to approximate the hazy density in the scene to obtain the weight coefficient, and then combining weighting coefficient to perform quadratic sinusoidal attenuation on the reconstructed dark channel to obtain the initial transmission. In order to obtain more precise transmission, the transmission is optimized by combining histogram equalization and fast-guided filtering. Finally, the haze-free image is restored by the atmospheric scattering model. Experimental results show that the proposed algorithm can effectively deal with the sky area, suppress the halo, restore the details of the image, and has appropriate the brightness and saturation.

Key words: image dehazing, sinusoidal attenuation, transmission

中图分类号:

TP751.1

梅葳, 李昕. 基于重构暗通道的二次正弦衰减的去雾算法[J]. 系统工程与电子技术, 2021, 43(5): 1169-1175.

Wei MEI, Xin LI. Dehazing algorithm based on reconstructed dark channel with quadratic sinusoidal attenuation[J]. Systems Engineering and Electronics, 2021, 43(5): 1169-1175.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 18

1	李晓聪. 图像去雾与增强技术的研究与应用[D]. 济南: 齐鲁工业大学, 2019.
	LI X C. Research and application of image defogging and enhancement technology[D]. Jinan: Qilu University of Technology, 2019.
2	易礼智. 雾霾环境下图像清晰化处理研究与应用[J]. 电脑与电信, 2019, 4 (2): 1- 4.
	YI L Z . Research and application of image clarity processing in haze environment[J]. Computer & Telecommunication, 2019, 4 (2): 1- 4.
3	QU Y F , ZOU Z F . Non-sky polarization-based dehazing algorithm for non-specular objects using polarization difference and global scene feature[J]. Optics Express, 2017, 25 (21): 25004- 25022. doi: 10.1364/OE.25.025004
4	CAI B L , XU X M , JIA K , et al. Dehazenet: an end-to-end system for single image haze removal[J]. IEEE Trans.on Image Processing, 2016, 25 (11): 5187- 5198. doi: 10.1109/TIP.2016.2598681
5	TAN R T. Visibility in bad weather from a single image[C]//Proc. of the IEEE 26th Conference on Computer Vision and Pattern Recognition, 2008.
6	杨燕, 陈高科, 周杰. 基于高斯权重衰减的迭代优化去雾算法[J]. 自动化学报, 2019, 45 (4): 819- 828.
	YANG Y , CHEN G K , ZHOU J . Iterative optimization defogging algorithm using Gaussian weight decay[J]. Acta Automatica Sinica, 2019, 45 (4): 819- 828.
7	杨燕, 陈高科. 基于光补偿和逐像素透射率的图像复原算法[J]. 通信学报, 2017, 38 (5): 48- 56.
	YANG Y , CHEN G K . Single image visibility restoration using optical compensation and pixel-by-pixel transmission estimation[J]. Journal on Communications, 2017, 38 (5): 48- 56.
8	FATTAL R . Single image dehazing[J]. ACM Transactions on Graphics, 2008, 27 (3): 547- 555.
9	TAREL J P, HAUTIÉRE N. Fast visibility restoration from a single color or gray level image[C]//Proc. of the IEEE 12th International Conference on Computer Vision, 2009.
10	ZHU Q S , MAI J M , SHAO L . A fast single image haze removal algorithm using color attenuation prior[J]. IEEE Trans.on Image Processing, 2015, 24 (11): 3522- 3533. doi: 10.1109/TIP.2015.2446191
11	HE K M , SUN J , TANG X O . Single image haze removal using dark channel prior[J]. IEEE Trans. on Pattern Analysis & Machine Intelligence, 2011, 33 (12): 2341- 2353.
12	MCCARTNRY E J . Optics of the atmosphere: scattering by mole-cules and particles[M]. New York: John Wiley and Sons, 1976: 421- 421.
13	YUCHENG Z M, SALMAN A. Image and depth estimation with mask-based lensless cameras[C]//Proc. of the IEEE 8th International Workshop on Computational Advances in Multi-Sensor Adaptive Processing, 2019.
14	HE K M , SUN J , TANG X O . Guided image filtering[J]. IEEE Trans. on Pattern Analysis & Machine Intelligence, 2013, 35 (6): 1397- 1409.
15	HE K M, SUN J. Fast guided filter[EB/OL]. [2015-05-05]. https://arxiv.org/abs/1505.00996v1.
16	GUO Y F , ZHANG Z S , YUAN H F , et al. Single remote-sensing image dehazing in HSI color space[J]. The Journal of the Korean Physical Society, 2019, 74 (8): 779- 784. doi: 10.3938/jkps.74.779
17	XU Y S, GUO X Q, WANG H Y, et al. Single image haze removal using light and dark channel prior[C]//Proc. of the IEEE 4th International Conference on Communications in China, 2016: 323-328.
18	XU Y , WEN J , FEI L K , et al. Review of video and image defogging algorithms and related studies on image restoration and enhancement[J]. IEEE Access, 2017, 4 (1): 165- 188.

算法	评价指标
	图 1			图 2			图 3			图 4
	E	R	T(s)	E	R	T(s)	E	R	T(s)	E	R	T(s)
Zhu提出的方法	0.23	2.26	2.03	0.13	1.33	1.83	0.13	1.86	1.08	0.06	2.31	3.76
Tarel提出的方法	0.29	2.28	2.29	0.32	1.73	1.91	0.22	1.73	1.91	0.28	1.62	4.29
He提出的方法	0.21	2.01	2.16	0.28	1.46	2.19	0.16	1.24	2.19	0.20	2.15	4.25
Fattal提出的方法	0.12	2.91	3.32	0.18	1.50	5.06	0.18	1.51	3.06	0.09	1.86	5.01
本文算法	0.31	2.96	2.26	0.37	2.09	2.05	0.26	2.11	2.05	0.25	2.36	5.63

[1]	眭萍, 毕笃彦, 马时平, 何林远. 基于局部一致性的马尔可夫随机场去雾[J]. 系统工程与电子技术, 2017, 39(5): 1154-1159.
[2]	曲晨, 毕笃彦, 严盛文, 何林远. 基于明暗像素先验的随机游走图像去雾[J]. 系统工程与电子技术, 2017, 39(10): 2368-2375.

基于重构暗通道的二次正弦衰减的去雾算法

Dehazing algorithm based on reconstructed dark channel with quadratic sinusoidal attenuation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 8

参考文献 18

相关文章 2

编辑推荐

Metrics

本文评价